Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description does not need to repeat safety traits. It adds the catalog-browse behavior, the returned fields, and pagination via offset, which is useful context beyond annotations. It does not go further into limits or other edge behaviors.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.